Get the latest tech news
Separating Data from Instructions in Prompting
Introducing Prompete - a LiteLLM wrapper for prompting with templates
We can leverage traditional software where it excels—such as using well-established algorithms for planning and deduction-based reasoning—while employing LLMs where they shine, namely in handling higher-level concepts and translating them into more precise machine code. Perhaps in the future, we’ll have separate inputs for LLMs: one channel for data structures and another for semantic instructions—just as we can currently feed them text and images. This mechanism of finding the template from the prompt data object is crucial to make it convenient.
Or read this on Hacker News
